Featured Posts
All writing →
Site Index
Full map →Recent Activity
All updates →A practical guide to hardware, OS, and llama.cpp tuning, built from a year of experiments on a single consumer CUDA workstation.
Squeezing every token per second
Every piece of content on this site now carries an authorship badge - a small indicator of how it was made:
I added this because transparency matters, especially as AI writing becomes indistinguishable from human writing. Most of my recent posts are AI-assisted - that's just how I work now. I'd rather be upfront about it than pretend otherwise.
This note itself is AI-generated. Fitting.
A data analyst's mostly futile quest for the perfect workflow.
AI coding prices got stupid this week.
| Model | Input | Output |
|---|---|---|
| Muse Spark 1.2 Contributor | $0.10 | $0.20 |
| DeepSeek V4 Flash | $0.14 | $0.28 |
| GPT-5.6 Luna | $0.20 | $1.20 |
| Luna via OpenRouter (50% off) | $0.10 | $0.60 |
Prices are per million tokens.
Muse Contributor is the cheapest of the bunch. Ten million input tokens and two million output tokens cost $1.40. The trade is permission for Meta to train on your prompts and completions, so I would keep work code far away from it.
DeepSeek V4 Flash is nearly as cheap without needing a special contributor tier, and its cached input price is a frankly stupid $0.0028 per million tokens.
Luna then went from cheap to silly. OpenAI dropped the direct API price to $0.20/$1.20, and OpenRouter is temporarily selling it at another 50% off ($0.10/$0.60).
Subscriptions are getting dragged into the fight too. OpenCode Go is $5 for the first month and $10/month after that, with Luna currently getting 2x usage limits.
Luna is still king for me, though.
By my rough usage-limit math, Luna Max on the $20 ChatGPT Plus plan works out to around 1.5 billion tokens a week. The exact number depends on how credits are counted, but the allowance is large enough that I have stopped thinking about individual requests. Max reasoning when I need it, fast mode almost everywhere else.
This is basically TPS over Quality again, except the cheap fast model is now also very good.
ChatGPT Plus. Luna Max. Fast mode. That is all I need.
Begun, the price wars have.
A practical tier list for coding and agentic AI models, with service comparisons and API pricing.
Quote Of The Day
The illiterate of the 21st century will not be those who cannot read and write, but those who cannot learn, unlearn, and relearn. - Alvin Toffler
